Preserving projection learning has been widely used in feature extraction and selection for unsupervised image classification. Generally, some related methods constructed a graph to represent the ...

Unsupervised feature selection is challenging in machine learning, pattern recognition, and data mining. The crucial difficulty is to learn a moderate subspace that preserves the intrinsic structure ...

This research addresses these limitations by proposing an innovative approach that integrates reinforcement learning and cognitive graphs to optimize learning paths in real-time. The proposed method ...

Contrastive learning has been widely used in graph representation learning, which extracts node or graph representations by contrasting positive and negative node pairs. It requires node ...

Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid ...

To address these challenges, we propose an adaptive graph learning framework for surgical workflow anticipation based on a novel spatial representation, featuring three key innovations.

Research team introduced Soft-GNN, a framework to train robust GNNs under noisy conditions. Soft-GNN mitigates label noise impact through dynamic data selection, achieving better performance and ...

The method performs adaptive masking through reconstruction loss, and jointly adaptive mask representation learning and clustering in an end-to-end unsupervised framework. The mutual information ...